In six small open-weight LLMs, jailbreak prompts are linearly separable in last-token embeddings by surface form, but not by refusal/compliance behavior.
Interventional Probing in High Dimensions: An NLI Case Study
1 Pith paper cite this work, alongside 4 external citations. Polarity classification is still indexing.
1
Pith paper citing it
4
external citations · OpenAlex
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometric Configurations of Perturbed Jailbreak Prompts
In six small open-weight LLMs, jailbreak prompts are linearly separable in last-token embeddings by surface form, but not by refusal/compliance behavior.